Separate histograms
A poor tissue segmentation includes multiple tissue types, leading to a wide distribution of intensity values and more variance.
On the other hand, a perfectly segmented left ventricle would contain only blood-related pixels, so the histogram of the segmented values should be roughly bell-shaped.
For this exercise, compare the intensity distributions within vol
for the listed sets of pixels. Use ndi.histogram
, which also accepts labels
and index
arguments.
This exercise is part of the course
Biomedical Image Analysis in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Create histograms for selected pixels
hist1 = ndi.histogram(vol, min=0, max=255, bins=256)
hist2 = ndi.histogram(vol, 0, 255, 256, labels=____)
hist3 = ndi.histogram(vol, 0, 255, 256, labels=____, index=____)